←Back to NewsAI News/Training InfrapaperTraining InfraOpen SourceTsinghua's Puro-2B Trains a Language Model for Less Than One GPU RentalA Tsinghua team trained a 2B language model from scratch on consumer RTX 5090s for under $6,900, matching Qwen2.5-1.5B and open-sourcing everything.SourceAlphaSignalPublishedSep 1, 2026, 7:07 PMAuthorAlphaSignal NewsroomRead1 min readA Tsinghua team trained a 2B language model from scratch on consumer RTX 5090s for under $6,900, matching Qwen2.5-1.5B and open-sourcing everything.Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.Read original report ↗Next readsAlphaSignal · repoStanford's Marin Trains a 535B Open Model Anyone Can Watch LiveAlphaSignal · repoTencent Releases Octop, a Self-Hosted Multi-User AI Platform in One Processbolt.new · newsBolt Adds DeepSeek V4.1 Flash at 10x Cheaper Than V4 Pro
